《初级》Flink WordCount练习

import org.apache.flink.api.common.JobExecutionResult;
import org.apache.flink.api.common.accumulators.IntCounter;
import org.apache.flink.api.common.functions.RichFlatMapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.util.Collector;

public class WordCount {

	// *************************************************************************
	//     PROGRAM
	// *************************************************************************

	public static void main(String[] args) throws Exception {

		//1、获取命令行参数
		final ParameterTool params = ParameterTool.fromArgs(args);

		//2、 set up the execution environment
		final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

		// make parameters available in the web interface
		env.getConfig().setGlobalJobParameters(params);

		// get input data
		DataSet<String> text;
		if (params.has("input")) {
			// read the text file from given input path
			text = env.readTextFile(params.get("input"));
		} else {
			// get default test text data
			System.out.println("Executing WordCount example with default input data set.");
			System.out.println("Use --input to specify file input.");
			text = WordCountData.getDefaultTextLineDataSet(env);
		}


		DataSet<Tuple2<String, Integer>> counts =
				// split up the lines in pairs (2-tuples) containing: (word,1)
				text.flatMap(new Tokenizer())
				// group by the tuple field "0" and sum up tuple field "1"
				.groupBy(0)
				.sum(1);

		// emit result
		if (params.has("output")) {
			counts.writeAsCsv(params.get("output"), "\n", " ");
			// execute program
			JobExecutionResult jobExecutionResult =env.execute("WordCount Example");
			jobExecutionResult.getAccumulatorResult("num-lines").toString();

		} else {
			System.out.println("Printing result to stdout. Use --output to specify output path.");
			counts.print();
		}

	}

	// *************************************************************************
	//     USER FUNCTIONS
	// *************************************************************************

	/**
	 * Implements the string tokenizer that splits sentences into words as a user-defined
	 * FlatMapFunction. The function takes a line (String) and splits it into
	 * multiple pairs in the form of "(word,1)" ({@code Tuple2<String, Integer>}).
	 */
	public static final class Tokenizer extends RichFlatMapFunction<String, Tuple2<String, Integer>> {
		private IntCounter numLines = new IntCounter();

		@Override
		public void open(Configuration parameters) throws Exception {
			getRuntimeContext().addAccumulator("num-lines", this.numLines);
			super.open(parameters);
		}

		@Override
		public void close() throws Exception {
			super.close();
		}

		@Override
		public void flatMap(String value, Collector<Tuple2<String, Integer>> out) {
			this.numLines.add(1);
			// normalize and split the line
			//"To be, or not to be,--that is the question:--",
			String[] tokens = value.toLowerCase().split("\\W+");

			// emit the pairs
			for (String token : tokens) {
				if (token.length() > 0) {
					out.collect(new Tuple2<>(token, 1));
				}
			}
		}
	}

}

 

 

 

import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;

public class WordCountData {

	public static final String[] WORDS = new String[] {
		"To be, or not to be,--that is the question:--",
		"Whether 'tis nobler in the mind to suffer",
		"The slings and arrows of outrageous fortune",
		"Or to take arms against a sea of troubles,",
		"And by opposing end them?--To die,--to sleep,--",
		"No more; and by a sleep to say we end",
		"The heartache, and the thousand natural shocks",
		"That flesh is heir to,--'tis a consummation",
		"Devoutly to be wish'd. To die,--to sleep;--",
		"To sleep! perchance to dream:--ay, there's the rub;",
		"For in that sleep of death what dreams may come,",
		"When we have shuffled off this mortal coil,",
		"Must give us pause: there's the respect",
		"That makes calamity of so long life;",
		"For who would bear the whips and scorns of time,",
		"The oppressor's wrong, the proud man's contumely,",
		"The pangs of despis'd love, the law's delay,",
		"The insolence of office, and the spurns",
		"That patient merit of the unworthy takes,",
		"When he himself might his quietus make",
		"With a bare bodkin? who would these fardels bear,",
		"To grunt and sweat under a weary life,",
		"But that the dread of something after death,--",
		"The undiscover'd country, from whose bourn",
		"No traveller returns,--puzzles the will,",
		"And makes us rather bear those ills we have",
		"Than fly to others that we know not of?",
		"Thus conscience does make cowards of us all;",
		"And thus the native hue of resolution",
		"Is sicklied o'er with the pale cast of thought;",
		"And enterprises of great pith and moment,",
		"With this regard, their currents turn awry,",
		"And lose the name of action.--Soft you now!",
		"The fair Ophelia!--Nymph, in thy orisons",
		"Be all my sins remember'd."
	};

	public static DataSet<String> getDefaultTextLineDataSet(ExecutionEnvironment env) {
		return env.fromElements(WORDS);
	}
}

加微信拉微信交流群

微信：weixin605405145